neighbour.c 64.6 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30
/*
 *	Generic address resolution entity
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *	Alexey Kuznetsov	<kuznet@ms2.inr.ac.ru>
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 *
 *	Fixes:
 *	Vitaly E. Lavrov	releasing NULL neighbor in neigh_add.
 *	Harald Welte		Add neighbour cache statistics like rtstat
 */

#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/times.h>
#include <net/neighbour.h>
#include <net/dst.h>
#include <net/sock.h>
31
#include <net/netevent.h>
32
#include <net/netlink.h>
L
Linus Torvalds 已提交
33 34
#include <linux/rtnetlink.h>
#include <linux/random.h>
35
#include <linux/string.h>
L
Linus Torvalds 已提交
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63

#define NEIGH_DEBUG 1

#define NEIGH_PRINTK(x...) printk(x)
#define NEIGH_NOPRINTK(x...) do { ; } while(0)
#define NEIGH_PRINTK0 NEIGH_PRINTK
#define NEIGH_PRINTK1 NEIGH_NOPRINTK
#define NEIGH_PRINTK2 NEIGH_NOPRINTK

#if NEIGH_DEBUG >= 1
#undef NEIGH_PRINTK1
#define NEIGH_PRINTK1 NEIGH_PRINTK
#endif
#if NEIGH_DEBUG >= 2
#undef NEIGH_PRINTK2
#define NEIGH_PRINTK2 NEIGH_PRINTK
#endif

#define PNEIGH_HASHMASK		0xF

static void neigh_timer_handler(unsigned long arg);
#ifdef CONFIG_ARPD
static void neigh_app_notify(struct neighbour *n);
#endif
static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev);

static struct neigh_table *neigh_tables;
64
#ifdef CONFIG_PROC_FS
65
static const struct file_operations neigh_stat_seq_fops;
66
#endif
L
Linus Torvalds 已提交
67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142

/*
   Neighbour hash table buckets are protected with rwlock tbl->lock.

   - All the scans/updates to hash buckets MUST be made under this lock.
   - NOTHING clever should be made under this lock: no callbacks
     to protocol backends, no attempts to send something to network.
     It will result in deadlocks, if backend/driver wants to use neighbour
     cache.
   - If the entry requires some non-trivial actions, increase
     its reference count and release table lock.

   Neighbour entries are protected:
   - with reference count.
   - with rwlock neigh->lock

   Reference count prevents destruction.

   neigh->lock mainly serializes ll address data and its validity state.
   However, the same lock is used to protect another entry fields:
    - timer
    - resolution queue

   Again, nothing clever shall be made under neigh->lock,
   the most complicated procedure, which we allow is dev->hard_header.
   It is supposed, that dev->hard_header is simplistic and does
   not make callbacks to neighbour tables.

   The last lock is neigh_tbl_lock. It is pure SMP lock, protecting
   list of neighbour tables. This list is used only in process context,
 */

static DEFINE_RWLOCK(neigh_tbl_lock);

static int neigh_blackhole(struct sk_buff *skb)
{
	kfree_skb(skb);
	return -ENETDOWN;
}

/*
 * It is random distribution in the interval (1/2)*base...(3/2)*base.
 * It corresponds to default IPv6 settings and is not overridable,
 * because it is really reasonable choice.
 */

unsigned long neigh_rand_reach_time(unsigned long base)
{
	return (base ? (net_random() % base) + (base >> 1) : 0);
}


static int neigh_forced_gc(struct neigh_table *tbl)
{
	int shrunk = 0;
	int i;

	NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);

	write_lock_bh(&tbl->lock);
	for (i = 0; i <= tbl->hash_mask; i++) {
		struct neighbour *n, **np;

		np = &tbl->hash_buckets[i];
		while ((n = *np) != NULL) {
			/* Neighbour record may be discarded if:
			 * - nobody refers to it.
			 * - it is not permanent
			 */
			write_lock(&n->lock);
			if (atomic_read(&n->refcnt) == 1 &&
			    !(n->nud_state & NUD_PERMANENT)) {
				*np	= n->next;
				n->dead = 1;
				shrunk	= 1;
				write_unlock(&n->lock);
143 144
				if (n->parms->neigh_cleanup)
					n->parms->neigh_cleanup(n);
L
Linus Torvalds 已提交
145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179
				neigh_release(n);
				continue;
			}
			write_unlock(&n->lock);
			np = &n->next;
		}
	}

	tbl->last_flush = jiffies;

	write_unlock_bh(&tbl->lock);

	return shrunk;
}

static int neigh_del_timer(struct neighbour *n)
{
	if ((n->nud_state & NUD_IN_TIMER) &&
	    del_timer(&n->timer)) {
		neigh_release(n);
		return 1;
	}
	return 0;
}

static void pneigh_queue_purge(struct sk_buff_head *list)
{
	struct sk_buff *skb;

	while ((skb = skb_dequeue(list)) != NULL) {
		dev_put(skb->dev);
		kfree_skb(skb);
	}
}

180
static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev)
L
Linus Torvalds 已提交
181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215
{
	int i;

	for (i = 0; i <= tbl->hash_mask; i++) {
		struct neighbour *n, **np = &tbl->hash_buckets[i];

		while ((n = *np) != NULL) {
			if (dev && n->dev != dev) {
				np = &n->next;
				continue;
			}
			*np = n->next;
			write_lock(&n->lock);
			neigh_del_timer(n);
			n->dead = 1;

			if (atomic_read(&n->refcnt) != 1) {
				/* The most unpleasant situation.
				   We must destroy neighbour entry,
				   but someone still uses it.

				   The destroy will be delayed until
				   the last user releases us, but
				   we must kill timers etc. and move
				   it to safe state.
				 */
				skb_queue_purge(&n->arp_queue);
				n->output = neigh_blackhole;
				if (n->nud_state & NUD_VALID)
					n->nud_state = NUD_NOARP;
				else
					n->nud_state = NUD_NONE;
				NEIGH_PRINTK2("neigh %p is stray.\n", n);
			}
			write_unlock(&n->lock);
216 217
			if (n->parms->neigh_cleanup)
				n->parms->neigh_cleanup(n);
L
Linus Torvalds 已提交
218 219 220
			neigh_release(n);
		}
	}
221
}
L
Linus Torvalds 已提交
222

223 224 225 226 227 228 229 230 231 232 233
void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev)
{
	write_lock_bh(&tbl->lock);
	neigh_flush_dev(tbl, dev);
	write_unlock_bh(&tbl->lock);
}

int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
{
	write_lock_bh(&tbl->lock);
	neigh_flush_dev(tbl, dev);
L
Linus Torvalds 已提交
234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256
	pneigh_ifdown(tbl, dev);
	write_unlock_bh(&tbl->lock);

	del_timer_sync(&tbl->proxy_timer);
	pneigh_queue_purge(&tbl->proxy_queue);
	return 0;
}

static struct neighbour *neigh_alloc(struct neigh_table *tbl)
{
	struct neighbour *n = NULL;
	unsigned long now = jiffies;
	int entries;

	entries = atomic_inc_return(&tbl->entries) - 1;
	if (entries >= tbl->gc_thresh3 ||
	    (entries >= tbl->gc_thresh2 &&
	     time_after(now, tbl->last_flush + 5 * HZ))) {
		if (!neigh_forced_gc(tbl) &&
		    entries >= tbl->gc_thresh3)
			goto out_entries;
	}

257
	n = kmem_cache_zalloc(tbl->kmem_cachep, GFP_ATOMIC);
L
Linus Torvalds 已提交
258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288
	if (!n)
		goto out_entries;

	skb_queue_head_init(&n->arp_queue);
	rwlock_init(&n->lock);
	n->updated	  = n->used = now;
	n->nud_state	  = NUD_NONE;
	n->output	  = neigh_blackhole;
	n->parms	  = neigh_parms_clone(&tbl->parms);
	init_timer(&n->timer);
	n->timer.function = neigh_timer_handler;
	n->timer.data	  = (unsigned long)n;

	NEIGH_CACHE_STAT_INC(tbl, allocs);
	n->tbl		  = tbl;
	atomic_set(&n->refcnt, 1);
	n->dead		  = 1;
out:
	return n;

out_entries:
	atomic_dec(&tbl->entries);
	goto out;
}

static struct neighbour **neigh_hash_alloc(unsigned int entries)
{
	unsigned long size = entries * sizeof(struct neighbour *);
	struct neighbour **ret;

	if (size <= PAGE_SIZE) {
A
Andrew Morton 已提交
289
		ret = kzalloc(size, GFP_ATOMIC);
L
Linus Torvalds 已提交
290 291
	} else {
		ret = (struct neighbour **)
A
Andrew Morton 已提交
292
		      __get_free_pages(GFP_ATOMIC|__GFP_ZERO, get_order(size));
L
Linus Torvalds 已提交
293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347
	}
	return ret;
}

static void neigh_hash_free(struct neighbour **hash, unsigned int entries)
{
	unsigned long size = entries * sizeof(struct neighbour *);

	if (size <= PAGE_SIZE)
		kfree(hash);
	else
		free_pages((unsigned long)hash, get_order(size));
}

static void neigh_hash_grow(struct neigh_table *tbl, unsigned long new_entries)
{
	struct neighbour **new_hash, **old_hash;
	unsigned int i, new_hash_mask, old_entries;

	NEIGH_CACHE_STAT_INC(tbl, hash_grows);

	BUG_ON(new_entries & (new_entries - 1));
	new_hash = neigh_hash_alloc(new_entries);
	if (!new_hash)
		return;

	old_entries = tbl->hash_mask + 1;
	new_hash_mask = new_entries - 1;
	old_hash = tbl->hash_buckets;

	get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd));
	for (i = 0; i < old_entries; i++) {
		struct neighbour *n, *next;

		for (n = old_hash[i]; n; n = next) {
			unsigned int hash_val = tbl->hash(n->primary_key, n->dev);

			hash_val &= new_hash_mask;
			next = n->next;

			n->next = new_hash[hash_val];
			new_hash[hash_val] = n;
		}
	}
	tbl->hash_buckets = new_hash;
	tbl->hash_mask = new_hash_mask;

	neigh_hash_free(old_hash, old_entries);
}

struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
			       struct net_device *dev)
{
	struct neighbour *n;
	int key_len = tbl->key_len;
348
	u32 hash_val = tbl->hash(pkey, dev);
349

L
Linus Torvalds 已提交
350 351 352
	NEIGH_CACHE_STAT_INC(tbl, lookups);

	read_lock_bh(&tbl->lock);
353
	for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) {
L
Linus Torvalds 已提交
354 355 356 357 358 359 360 361 362 363 364 365 366 367
		if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) {
			neigh_hold(n);
			NEIGH_CACHE_STAT_INC(tbl, hits);
			break;
		}
	}
	read_unlock_bh(&tbl->lock);
	return n;
}

struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, const void *pkey)
{
	struct neighbour *n;
	int key_len = tbl->key_len;
368
	u32 hash_val = tbl->hash(pkey, NULL);
L
Linus Torvalds 已提交
369 370 371 372

	NEIGH_CACHE_STAT_INC(tbl, lookups);

	read_lock_bh(&tbl->lock);
373
	for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) {
L
Linus Torvalds 已提交
374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580
		if (!memcmp(n->primary_key, pkey, key_len)) {
			neigh_hold(n);
			NEIGH_CACHE_STAT_INC(tbl, hits);
			break;
		}
	}
	read_unlock_bh(&tbl->lock);
	return n;
}

struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey,
			       struct net_device *dev)
{
	u32 hash_val;
	int key_len = tbl->key_len;
	int error;
	struct neighbour *n1, *rc, *n = neigh_alloc(tbl);

	if (!n) {
		rc = ERR_PTR(-ENOBUFS);
		goto out;
	}

	memcpy(n->primary_key, pkey, key_len);
	n->dev = dev;
	dev_hold(dev);

	/* Protocol specific setup. */
	if (tbl->constructor &&	(error = tbl->constructor(n)) < 0) {
		rc = ERR_PTR(error);
		goto out_neigh_release;
	}

	/* Device specific setup. */
	if (n->parms->neigh_setup &&
	    (error = n->parms->neigh_setup(n)) < 0) {
		rc = ERR_PTR(error);
		goto out_neigh_release;
	}

	n->confirmed = jiffies - (n->parms->base_reachable_time << 1);

	write_lock_bh(&tbl->lock);

	if (atomic_read(&tbl->entries) > (tbl->hash_mask + 1))
		neigh_hash_grow(tbl, (tbl->hash_mask + 1) << 1);

	hash_val = tbl->hash(pkey, dev) & tbl->hash_mask;

	if (n->parms->dead) {
		rc = ERR_PTR(-EINVAL);
		goto out_tbl_unlock;
	}

	for (n1 = tbl->hash_buckets[hash_val]; n1; n1 = n1->next) {
		if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) {
			neigh_hold(n1);
			rc = n1;
			goto out_tbl_unlock;
		}
	}

	n->next = tbl->hash_buckets[hash_val];
	tbl->hash_buckets[hash_val] = n;
	n->dead = 0;
	neigh_hold(n);
	write_unlock_bh(&tbl->lock);
	NEIGH_PRINTK2("neigh %p is created.\n", n);
	rc = n;
out:
	return rc;
out_tbl_unlock:
	write_unlock_bh(&tbl->lock);
out_neigh_release:
	neigh_release(n);
	goto out;
}

struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, const void *pkey,
				    struct net_device *dev, int creat)
{
	struct pneigh_entry *n;
	int key_len = tbl->key_len;
	u32 hash_val = *(u32 *)(pkey + key_len - 4);

	hash_val ^= (hash_val >> 16);
	hash_val ^= hash_val >> 8;
	hash_val ^= hash_val >> 4;
	hash_val &= PNEIGH_HASHMASK;

	read_lock_bh(&tbl->lock);

	for (n = tbl->phash_buckets[hash_val]; n; n = n->next) {
		if (!memcmp(n->key, pkey, key_len) &&
		    (n->dev == dev || !n->dev)) {
			read_unlock_bh(&tbl->lock);
			goto out;
		}
	}
	read_unlock_bh(&tbl->lock);
	n = NULL;
	if (!creat)
		goto out;

	n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL);
	if (!n)
		goto out;

	memcpy(n->key, pkey, key_len);
	n->dev = dev;
	if (dev)
		dev_hold(dev);

	if (tbl->pconstructor && tbl->pconstructor(n)) {
		if (dev)
			dev_put(dev);
		kfree(n);
		n = NULL;
		goto out;
	}

	write_lock_bh(&tbl->lock);
	n->next = tbl->phash_buckets[hash_val];
	tbl->phash_buckets[hash_val] = n;
	write_unlock_bh(&tbl->lock);
out:
	return n;
}


int pneigh_delete(struct neigh_table *tbl, const void *pkey,
		  struct net_device *dev)
{
	struct pneigh_entry *n, **np;
	int key_len = tbl->key_len;
	u32 hash_val = *(u32 *)(pkey + key_len - 4);

	hash_val ^= (hash_val >> 16);
	hash_val ^= hash_val >> 8;
	hash_val ^= hash_val >> 4;
	hash_val &= PNEIGH_HASHMASK;

	write_lock_bh(&tbl->lock);
	for (np = &tbl->phash_buckets[hash_val]; (n = *np) != NULL;
	     np = &n->next) {
		if (!memcmp(n->key, pkey, key_len) && n->dev == dev) {
			*np = n->next;
			write_unlock_bh(&tbl->lock);
			if (tbl->pdestructor)
				tbl->pdestructor(n);
			if (n->dev)
				dev_put(n->dev);
			kfree(n);
			return 0;
		}
	}
	write_unlock_bh(&tbl->lock);
	return -ENOENT;
}

static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
{
	struct pneigh_entry *n, **np;
	u32 h;

	for (h = 0; h <= PNEIGH_HASHMASK; h++) {
		np = &tbl->phash_buckets[h];
		while ((n = *np) != NULL) {
			if (!dev || n->dev == dev) {
				*np = n->next;
				if (tbl->pdestructor)
					tbl->pdestructor(n);
				if (n->dev)
					dev_put(n->dev);
				kfree(n);
				continue;
			}
			np = &n->next;
		}
	}
	return -ENOENT;
}


/*
 *	neighbour must already be out of the table;
 *
 */
void neigh_destroy(struct neighbour *neigh)
{
	struct hh_cache *hh;

	NEIGH_CACHE_STAT_INC(neigh->tbl, destroys);

	if (!neigh->dead) {
		printk(KERN_WARNING
		       "Destroying alive neighbour %p\n", neigh);
		dump_stack();
		return;
	}

	if (neigh_del_timer(neigh))
		printk(KERN_WARNING "Impossible event.\n");

	while ((hh = neigh->hh) != NULL) {
		neigh->hh = hh->hh_next;
		hh->hh_next = NULL;
581 582

		write_seqlock_bh(&hh->hh_lock);
L
Linus Torvalds 已提交
583
		hh->hh_output = neigh_blackhole;
584
		write_sequnlock_bh(&hh->hh_lock);
L
Linus Torvalds 已提交
585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678
		if (atomic_dec_and_test(&hh->hh_refcnt))
			kfree(hh);
	}

	skb_queue_purge(&neigh->arp_queue);

	dev_put(neigh->dev);
	neigh_parms_put(neigh->parms);

	NEIGH_PRINTK2("neigh %p is destroyed.\n", neigh);

	atomic_dec(&neigh->tbl->entries);
	kmem_cache_free(neigh->tbl->kmem_cachep, neigh);
}

/* Neighbour state is suspicious;
   disable fast path.

   Called with write_locked neigh.
 */
static void neigh_suspect(struct neighbour *neigh)
{
	struct hh_cache *hh;

	NEIGH_PRINTK2("neigh %p is suspected.\n", neigh);

	neigh->output = neigh->ops->output;

	for (hh = neigh->hh; hh; hh = hh->hh_next)
		hh->hh_output = neigh->ops->output;
}

/* Neighbour state is OK;
   enable fast path.

   Called with write_locked neigh.
 */
static void neigh_connect(struct neighbour *neigh)
{
	struct hh_cache *hh;

	NEIGH_PRINTK2("neigh %p is connected.\n", neigh);

	neigh->output = neigh->ops->connected_output;

	for (hh = neigh->hh; hh; hh = hh->hh_next)
		hh->hh_output = neigh->ops->hh_output;
}

static void neigh_periodic_timer(unsigned long arg)
{
	struct neigh_table *tbl = (struct neigh_table *)arg;
	struct neighbour *n, **np;
	unsigned long expire, now = jiffies;

	NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs);

	write_lock(&tbl->lock);

	/*
	 *	periodically recompute ReachableTime from random function
	 */

	if (time_after(now, tbl->last_rand + 300 * HZ)) {
		struct neigh_parms *p;
		tbl->last_rand = now;
		for (p = &tbl->parms; p; p = p->next)
			p->reachable_time =
				neigh_rand_reach_time(p->base_reachable_time);
	}

	np = &tbl->hash_buckets[tbl->hash_chain_gc];
	tbl->hash_chain_gc = ((tbl->hash_chain_gc + 1) & tbl->hash_mask);

	while ((n = *np) != NULL) {
		unsigned int state;

		write_lock(&n->lock);

		state = n->nud_state;
		if (state & (NUD_PERMANENT | NUD_IN_TIMER)) {
			write_unlock(&n->lock);
			goto next_elt;
		}

		if (time_before(n->used, n->confirmed))
			n->used = n->confirmed;

		if (atomic_read(&n->refcnt) == 1 &&
		    (state == NUD_FAILED ||
		     time_after(now, n->used + n->parms->gc_staletime))) {
			*np = n->next;
			n->dead = 1;
			write_unlock(&n->lock);
679 680
			if (n->parms->neigh_cleanup)
				n->parms->neigh_cleanup(n);
L
Linus Torvalds 已提交
681 682 683 684 685 686 687 688 689
			neigh_release(n);
			continue;
		}
		write_unlock(&n->lock);

next_elt:
		np = &n->next;
	}

690 691 692
	/* Cycle through all hash buckets every base_reachable_time/2 ticks.
	 * ARP entry timeouts range from 1/2 base_reachable_time to 3/2
	 * base_reachable_time.
L
Linus Torvalds 已提交
693 694 695 696 697 698
	 */
	expire = tbl->parms.base_reachable_time >> 1;
	expire /= (tbl->hash_mask + 1);
	if (!expire)
		expire = 1;

699 700 701 702
	if (expire>HZ)
		mod_timer(&tbl->gc_timer, round_jiffies(now + expire));
	else
		mod_timer(&tbl->gc_timer, now + expire);
L
Linus Torvalds 已提交
703 704 705 706 707 708 709 710 711 712 713 714

	write_unlock(&tbl->lock);
}

static __inline__ int neigh_max_probes(struct neighbour *n)
{
	struct neigh_parms *p = n->parms;
	return (n->nud_state & NUD_PROBE ?
		p->ucast_probes :
		p->ucast_probes + p->app_probes + p->mcast_probes);
}

715 716 717 718 719
static inline void neigh_add_timer(struct neighbour *n, unsigned long when)
{
	if (unlikely(mod_timer(&n->timer, when))) {
		printk("NEIGH: BUG, double timer add, state is %x\n",
		       n->nud_state);
720
		dump_stack();
721 722
	}
}
L
Linus Torvalds 已提交
723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746

/* Called when a timer expires for a neighbour entry. */

static void neigh_timer_handler(unsigned long arg)
{
	unsigned long now, next;
	struct neighbour *neigh = (struct neighbour *)arg;
	unsigned state;
	int notify = 0;

	write_lock(&neigh->lock);

	state = neigh->nud_state;
	now = jiffies;
	next = now + HZ;

	if (!(state & NUD_IN_TIMER)) {
#ifndef CONFIG_SMP
		printk(KERN_WARNING "neigh: timer & !nud_in_timer\n");
#endif
		goto out;
	}

	if (state & NUD_REACHABLE) {
747
		if (time_before_eq(now,
L
Linus Torvalds 已提交
748 749 750 751 752 753 754
				   neigh->confirmed + neigh->parms->reachable_time)) {
			NEIGH_PRINTK2("neigh %p is still alive.\n", neigh);
			next = neigh->confirmed + neigh->parms->reachable_time;
		} else if (time_before_eq(now,
					  neigh->used + neigh->parms->delay_probe_time)) {
			NEIGH_PRINTK2("neigh %p is delayed.\n", neigh);
			neigh->nud_state = NUD_DELAY;
755
			neigh->updated = jiffies;
L
Linus Torvalds 已提交
756 757 758 759 760
			neigh_suspect(neigh);
			next = now + neigh->parms->delay_probe_time;
		} else {
			NEIGH_PRINTK2("neigh %p is suspected.\n", neigh);
			neigh->nud_state = NUD_STALE;
761
			neigh->updated = jiffies;
L
Linus Torvalds 已提交
762
			neigh_suspect(neigh);
763
			notify = 1;
L
Linus Torvalds 已提交
764 765
		}
	} else if (state & NUD_DELAY) {
766
		if (time_before_eq(now,
L
Linus Torvalds 已提交
767 768 769
				   neigh->confirmed + neigh->parms->delay_probe_time)) {
			NEIGH_PRINTK2("neigh %p is now reachable.\n", neigh);
			neigh->nud_state = NUD_REACHABLE;
770
			neigh->updated = jiffies;
L
Linus Torvalds 已提交
771
			neigh_connect(neigh);
772
			notify = 1;
L
Linus Torvalds 已提交
773 774 775 776
			next = neigh->confirmed + neigh->parms->reachable_time;
		} else {
			NEIGH_PRINTK2("neigh %p is probed.\n", neigh);
			neigh->nud_state = NUD_PROBE;
777
			neigh->updated = jiffies;
L
Linus Torvalds 已提交
778 779 780 781 782 783 784 785 786 787 788 789 790
			atomic_set(&neigh->probes, 0);
			next = now + neigh->parms->retrans_time;
		}
	} else {
		/* NUD_PROBE|NUD_INCOMPLETE */
		next = now + neigh->parms->retrans_time;
	}

	if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) &&
	    atomic_read(&neigh->probes) >= neigh_max_probes(neigh)) {
		struct sk_buff *skb;

		neigh->nud_state = NUD_FAILED;
791
		neigh->updated = jiffies;
L
Linus Torvalds 已提交
792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812
		notify = 1;
		NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed);
		NEIGH_PRINTK2("neigh %p is failed.\n", neigh);

		/* It is very thin place. report_unreachable is very complicated
		   routine. Particularly, it can hit the same neighbour entry!

		   So that, we try to be accurate and avoid dead loop. --ANK
		 */
		while (neigh->nud_state == NUD_FAILED &&
		       (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) {
			write_unlock(&neigh->lock);
			neigh->ops->error_report(neigh, skb);
			write_lock(&neigh->lock);
		}
		skb_queue_purge(&neigh->arp_queue);
	}

	if (neigh->nud_state & NUD_IN_TIMER) {
		if (time_before(next, jiffies + HZ/2))
			next = jiffies + HZ/2;
813 814
		if (!mod_timer(&neigh->timer, next))
			neigh_hold(neigh);
L
Linus Torvalds 已提交
815 816 817 818 819 820 821 822 823 824 825 826 827 828 829
	}
	if (neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) {
		struct sk_buff *skb = skb_peek(&neigh->arp_queue);
		/* keep skb alive even if arp_queue overflows */
		if (skb)
			skb_get(skb);
		write_unlock(&neigh->lock);
		neigh->ops->solicit(neigh, skb);
		atomic_inc(&neigh->probes);
		if (skb)
			kfree_skb(skb);
	} else {
out:
		write_unlock(&neigh->lock);
	}
830 831
	if (notify)
		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
L
Linus Torvalds 已提交
832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851

#ifdef CONFIG_ARPD
	if (notify && neigh->parms->app_probes)
		neigh_app_notify(neigh);
#endif
	neigh_release(neigh);
}

int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
{
	int rc;
	unsigned long now;

	write_lock_bh(&neigh->lock);

	rc = 0;
	if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
		goto out_unlock_bh;

	now = jiffies;
852

L
Linus Torvalds 已提交
853 854 855 856
	if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
		if (neigh->parms->mcast_probes + neigh->parms->app_probes) {
			atomic_set(&neigh->probes, neigh->parms->ucast_probes);
			neigh->nud_state     = NUD_INCOMPLETE;
857
			neigh->updated = jiffies;
L
Linus Torvalds 已提交
858
			neigh_hold(neigh);
859
			neigh_add_timer(neigh, now + 1);
L
Linus Torvalds 已提交
860 861
		} else {
			neigh->nud_state = NUD_FAILED;
862
			neigh->updated = jiffies;
L
Linus Torvalds 已提交
863 864 865 866 867 868 869 870 871 872
			write_unlock_bh(&neigh->lock);

			if (skb)
				kfree_skb(skb);
			return 1;
		}
	} else if (neigh->nud_state & NUD_STALE) {
		NEIGH_PRINTK2("neigh %p is delayed.\n", neigh);
		neigh_hold(neigh);
		neigh->nud_state = NUD_DELAY;
873
		neigh->updated = jiffies;
874 875
		neigh_add_timer(neigh,
				jiffies + neigh->parms->delay_probe_time);
L
Linus Torvalds 已提交
876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895
	}

	if (neigh->nud_state == NUD_INCOMPLETE) {
		if (skb) {
			if (skb_queue_len(&neigh->arp_queue) >=
			    neigh->parms->queue_len) {
				struct sk_buff *buff;
				buff = neigh->arp_queue.next;
				__skb_unlink(buff, &neigh->arp_queue);
				kfree_skb(buff);
			}
			__skb_queue_tail(&neigh->arp_queue, skb);
		}
		rc = 1;
	}
out_unlock_bh:
	write_unlock_bh(&neigh->lock);
	return rc;
}

896
static void neigh_update_hhs(struct neighbour *neigh)
L
Linus Torvalds 已提交
897 898 899 900 901 902 903
{
	struct hh_cache *hh;
	void (*update)(struct hh_cache*, struct net_device*, unsigned char *) =
		neigh->dev->header_cache_update;

	if (update) {
		for (hh = neigh->hh; hh; hh = hh->hh_next) {
904
			write_seqlock_bh(&hh->hh_lock);
L
Linus Torvalds 已提交
905
			update(hh, neigh->dev, neigh->ha);
906
			write_sequnlock_bh(&hh->hh_lock);
L
Linus Torvalds 已提交
907 908 909 910 911 912 913 914 915 916 917 918 919
		}
	}
}



/* Generic update routine.
   -- lladdr is new lladdr or NULL, if it is not supplied.
   -- new    is new state.
   -- flags
	NEIGH_UPDATE_F_OVERRIDE allows to override existing lladdr,
				if it is different.
	NEIGH_UPDATE_F_WEAK_OVERRIDE will suspect existing "connected"
920
				lladdr instead of overriding it
L
Linus Torvalds 已提交
921 922 923 924 925
				if it is different.
				It also allows to retain current state
				if lladdr is unchanged.
	NEIGH_UPDATE_F_ADMIN	means that the change is administrative.

926
	NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing
L
Linus Torvalds 已提交
927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948
				NTF_ROUTER flag.
	NEIGH_UPDATE_F_ISROUTER	indicates if the neighbour is known as
				a router.

   Caller MUST hold reference count on the entry.
 */

int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
		 u32 flags)
{
	u8 old;
	int err;
	int notify = 0;
	struct net_device *dev;
	int update_isrouter = 0;

	write_lock_bh(&neigh->lock);

	dev    = neigh->dev;
	old    = neigh->nud_state;
	err    = -EPERM;

949
	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
L
Linus Torvalds 已提交
950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972
	    (old & (NUD_NOARP | NUD_PERMANENT)))
		goto out;

	if (!(new & NUD_VALID)) {
		neigh_del_timer(neigh);
		if (old & NUD_CONNECTED)
			neigh_suspect(neigh);
		neigh->nud_state = new;
		err = 0;
		notify = old & NUD_VALID;
		goto out;
	}

	/* Compare new lladdr with cached one */
	if (!dev->addr_len) {
		/* First case: device needs no address. */
		lladdr = neigh->ha;
	} else if (lladdr) {
		/* The second case: if something is already cached
		   and a new address is proposed:
		   - compare new & old
		   - if they are different, check override flag
		 */
973
		if ((old & NUD_VALID) &&
L
Linus Torvalds 已提交
974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016
		    !memcmp(lladdr, neigh->ha, dev->addr_len))
			lladdr = neigh->ha;
	} else {
		/* No address is supplied; if we know something,
		   use it, otherwise discard the request.
		 */
		err = -EINVAL;
		if (!(old & NUD_VALID))
			goto out;
		lladdr = neigh->ha;
	}

	if (new & NUD_CONNECTED)
		neigh->confirmed = jiffies;
	neigh->updated = jiffies;

	/* If entry was valid and address is not changed,
	   do not change entry state, if new one is STALE.
	 */
	err = 0;
	update_isrouter = flags & NEIGH_UPDATE_F_OVERRIDE_ISROUTER;
	if (old & NUD_VALID) {
		if (lladdr != neigh->ha && !(flags & NEIGH_UPDATE_F_OVERRIDE)) {
			update_isrouter = 0;
			if ((flags & NEIGH_UPDATE_F_WEAK_OVERRIDE) &&
			    (old & NUD_CONNECTED)) {
				lladdr = neigh->ha;
				new = NUD_STALE;
			} else
				goto out;
		} else {
			if (lladdr == neigh->ha && new == NUD_STALE &&
			    ((flags & NEIGH_UPDATE_F_WEAK_OVERRIDE) ||
			     (old & NUD_CONNECTED))
			    )
				new = old;
		}
	}

	if (new != old) {
		neigh_del_timer(neigh);
		if (new & NUD_IN_TIMER) {
			neigh_hold(neigh);
1017 1018
			neigh_add_timer(neigh, (jiffies +
						((new & NUD_REACHABLE) ?
1019 1020
						 neigh->parms->reachable_time :
						 0)));
L
Linus Torvalds 已提交
1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062
		}
		neigh->nud_state = new;
	}

	if (lladdr != neigh->ha) {
		memcpy(&neigh->ha, lladdr, dev->addr_len);
		neigh_update_hhs(neigh);
		if (!(new & NUD_CONNECTED))
			neigh->confirmed = jiffies -
				      (neigh->parms->base_reachable_time << 1);
		notify = 1;
	}
	if (new == old)
		goto out;
	if (new & NUD_CONNECTED)
		neigh_connect(neigh);
	else
		neigh_suspect(neigh);
	if (!(old & NUD_VALID)) {
		struct sk_buff *skb;

		/* Again: avoid dead loop if something went wrong */

		while (neigh->nud_state & NUD_VALID &&
		       (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) {
			struct neighbour *n1 = neigh;
			write_unlock_bh(&neigh->lock);
			/* On shaper/eql skb->dst->neighbour != neigh :( */
			if (skb->dst && skb->dst->neighbour)
				n1 = skb->dst->neighbour;
			n1->output(skb);
			write_lock_bh(&neigh->lock);
		}
		skb_queue_purge(&neigh->arp_queue);
	}
out:
	if (update_isrouter) {
		neigh->flags = (flags & NEIGH_UPDATE_F_ISROUTER) ?
			(neigh->flags | NTF_ROUTER) :
			(neigh->flags & ~NTF_ROUTER);
	}
	write_unlock_bh(&neigh->lock);
1063 1064 1065

	if (notify)
		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
L
Linus Torvalds 已提交
1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079
#ifdef CONFIG_ARPD
	if (notify && neigh->parms->app_probes)
		neigh_app_notify(neigh);
#endif
	return err;
}

struct neighbour *neigh_event_ns(struct neigh_table *tbl,
				 u8 *lladdr, void *saddr,
				 struct net_device *dev)
{
	struct neighbour *neigh = __neigh_lookup(tbl, saddr, dev,
						 lladdr || !dev->addr_len);
	if (neigh)
1080
		neigh_update(neigh, lladdr, NUD_STALE,
L
Linus Torvalds 已提交
1081 1082 1083 1084 1085
			     NEIGH_UPDATE_F_OVERRIDE);
	return neigh;
}

static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst,
A
Al Viro 已提交
1086
			  __be16 protocol)
L
Linus Torvalds 已提交
1087 1088 1089 1090 1091 1092 1093 1094
{
	struct hh_cache	*hh;
	struct net_device *dev = dst->dev;

	for (hh = n->hh; hh; hh = hh->hh_next)
		if (hh->hh_type == protocol)
			break;

A
Andrew Morton 已提交
1095
	if (!hh && (hh = kzalloc(sizeof(*hh), GFP_ATOMIC)) != NULL) {
1096
		seqlock_init(&hh->hh_lock);
L
Linus Torvalds 已提交
1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131
		hh->hh_type = protocol;
		atomic_set(&hh->hh_refcnt, 0);
		hh->hh_next = NULL;
		if (dev->hard_header_cache(n, hh)) {
			kfree(hh);
			hh = NULL;
		} else {
			atomic_inc(&hh->hh_refcnt);
			hh->hh_next = n->hh;
			n->hh	    = hh;
			if (n->nud_state & NUD_CONNECTED)
				hh->hh_output = n->ops->hh_output;
			else
				hh->hh_output = n->ops->output;
		}
	}
	if (hh)	{
		atomic_inc(&hh->hh_refcnt);
		dst->hh = hh;
	}
}

/* This function can be used in contexts, where only old dev_queue_xmit
   worked, f.e. if you want to override normal output path (eql, shaper),
   but resolution is not made yet.
 */

int neigh_compat_output(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;

	__skb_pull(skb, skb->nh.raw - skb->data);

	if (dev->hard_header &&
	    dev->hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
1132
			     skb->len) < 0 &&
L
Linus Torvalds 已提交
1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220
	    dev->rebuild_header(skb))
		return 0;

	return dev_queue_xmit(skb);
}

/* Slow and careful. */

int neigh_resolve_output(struct sk_buff *skb)
{
	struct dst_entry *dst = skb->dst;
	struct neighbour *neigh;
	int rc = 0;

	if (!dst || !(neigh = dst->neighbour))
		goto discard;

	__skb_pull(skb, skb->nh.raw - skb->data);

	if (!neigh_event_send(neigh, skb)) {
		int err;
		struct net_device *dev = neigh->dev;
		if (dev->hard_header_cache && !dst->hh) {
			write_lock_bh(&neigh->lock);
			if (!dst->hh)
				neigh_hh_init(neigh, dst, dst->ops->protocol);
			err = dev->hard_header(skb, dev, ntohs(skb->protocol),
					       neigh->ha, NULL, skb->len);
			write_unlock_bh(&neigh->lock);
		} else {
			read_lock_bh(&neigh->lock);
			err = dev->hard_header(skb, dev, ntohs(skb->protocol),
					       neigh->ha, NULL, skb->len);
			read_unlock_bh(&neigh->lock);
		}
		if (err >= 0)
			rc = neigh->ops->queue_xmit(skb);
		else
			goto out_kfree_skb;
	}
out:
	return rc;
discard:
	NEIGH_PRINTK1("neigh_resolve_output: dst=%p neigh=%p\n",
		      dst, dst ? dst->neighbour : NULL);
out_kfree_skb:
	rc = -EINVAL;
	kfree_skb(skb);
	goto out;
}

/* As fast as possible without hh cache */

int neigh_connected_output(struct sk_buff *skb)
{
	int err;
	struct dst_entry *dst = skb->dst;
	struct neighbour *neigh = dst->neighbour;
	struct net_device *dev = neigh->dev;

	__skb_pull(skb, skb->nh.raw - skb->data);

	read_lock_bh(&neigh->lock);
	err = dev->hard_header(skb, dev, ntohs(skb->protocol),
			       neigh->ha, NULL, skb->len);
	read_unlock_bh(&neigh->lock);
	if (err >= 0)
		err = neigh->ops->queue_xmit(skb);
	else {
		err = -EINVAL;
		kfree_skb(skb);
	}
	return err;
}

static void neigh_proxy_process(unsigned long arg)
{
	struct neigh_table *tbl = (struct neigh_table *)arg;
	long sched_next = 0;
	unsigned long now = jiffies;
	struct sk_buff *skb;

	spin_lock(&tbl->proxy_queue.lock);

	skb = tbl->proxy_queue.next;

	while (skb != (struct sk_buff *)&tbl->proxy_queue) {
		struct sk_buff *back = skb;
1221
		long tdif = NEIGH_CB(back)->sched_next - now;
L
Linus Torvalds 已提交
1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251

		skb = skb->next;
		if (tdif <= 0) {
			struct net_device *dev = back->dev;
			__skb_unlink(back, &tbl->proxy_queue);
			if (tbl->proxy_redo && netif_running(dev))
				tbl->proxy_redo(back);
			else
				kfree_skb(back);

			dev_put(dev);
		} else if (!sched_next || tdif < sched_next)
			sched_next = tdif;
	}
	del_timer(&tbl->proxy_timer);
	if (sched_next)
		mod_timer(&tbl->proxy_timer, jiffies + sched_next);
	spin_unlock(&tbl->proxy_queue.lock);
}

void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
		    struct sk_buff *skb)
{
	unsigned long now = jiffies;
	unsigned long sched_next = now + (net_random() % p->proxy_delay);

	if (tbl->proxy_queue.qlen > p->proxy_qlen) {
		kfree_skb(skb);
		return;
	}
1252 1253 1254

	NEIGH_CB(skb)->sched_next = sched_next;
	NEIGH_CB(skb)->flags |= LOCALLY_ENQUEUED;
L
Linus Torvalds 已提交
1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272

	spin_lock(&tbl->proxy_queue.lock);
	if (del_timer(&tbl->proxy_timer)) {
		if (time_before(tbl->proxy_timer.expires, sched_next))
			sched_next = tbl->proxy_timer.expires;
	}
	dst_release(skb->dst);
	skb->dst = NULL;
	dev_hold(skb->dev);
	__skb_queue_tail(&tbl->proxy_queue, skb);
	mod_timer(&tbl->proxy_timer, sched_next);
	spin_unlock(&tbl->proxy_queue.lock);
}


struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
				      struct neigh_table *tbl)
{
1273
	struct neigh_parms *p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL);
L
Linus Torvalds 已提交
1274 1275 1276 1277 1278 1279 1280

	if (p) {
		p->tbl		  = tbl;
		atomic_set(&p->refcnt, 1);
		INIT_RCU_HEAD(&p->rcu_head);
		p->reachable_time =
				neigh_rand_reach_time(p->base_reachable_time);
1281 1282 1283 1284 1285 1286 1287 1288
		if (dev) {
			if (dev->neigh_setup && dev->neigh_setup(dev, p)) {
				kfree(p);
				return NULL;
			}

			dev_hold(dev);
			p->dev = dev;
L
Linus Torvalds 已提交
1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318
		}
		p->sysctl_table = NULL;
		write_lock_bh(&tbl->lock);
		p->next		= tbl->parms.next;
		tbl->parms.next = p;
		write_unlock_bh(&tbl->lock);
	}
	return p;
}

static void neigh_rcu_free_parms(struct rcu_head *head)
{
	struct neigh_parms *parms =
		container_of(head, struct neigh_parms, rcu_head);

	neigh_parms_put(parms);
}

void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms)
{
	struct neigh_parms **p;

	if (!parms || parms == &tbl->parms)
		return;
	write_lock_bh(&tbl->lock);
	for (p = &tbl->parms.next; *p; p = &(*p)->next) {
		if (*p == parms) {
			*p = parms->next;
			parms->dead = 1;
			write_unlock_bh(&tbl->lock);
1319 1320
			if (parms->dev)
				dev_put(parms->dev);
L
Linus Torvalds 已提交
1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333
			call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
			return;
		}
	}
	write_unlock_bh(&tbl->lock);
	NEIGH_PRINTK1("neigh_parms_release: not found\n");
}

void neigh_parms_destroy(struct neigh_parms *parms)
{
	kfree(parms);
}

1334 1335
static struct lock_class_key neigh_table_proxy_queue_class;

1336
void neigh_table_init_no_netlink(struct neigh_table *tbl)
L
Linus Torvalds 已提交
1337 1338 1339 1340 1341 1342 1343 1344 1345 1346
{
	unsigned long now = jiffies;
	unsigned long phsize;

	atomic_set(&tbl->parms.refcnt, 1);
	INIT_RCU_HEAD(&tbl->parms.rcu_head);
	tbl->parms.reachable_time =
			  neigh_rand_reach_time(tbl->parms.base_reachable_time);

	if (!tbl->kmem_cachep)
A
Alexey Dobriyan 已提交
1347 1348 1349 1350
		tbl->kmem_cachep =
			kmem_cache_create(tbl->id, tbl->entry_size, 0,
					  SLAB_HWCACHE_ALIGN|SLAB_PANIC,
					  NULL, NULL);
L
Linus Torvalds 已提交
1351 1352 1353
	tbl->stats = alloc_percpu(struct neigh_statistics);
	if (!tbl->stats)
		panic("cannot create neighbour cache statistics");
1354

L
Linus Torvalds 已提交
1355 1356
#ifdef CONFIG_PROC_FS
	tbl->pde = create_proc_entry(tbl->id, 0, proc_net_stat);
1357
	if (!tbl->pde)
L
Linus Torvalds 已提交
1358 1359 1360 1361 1362 1363 1364 1365 1366
		panic("cannot create neighbour proc dir entry");
	tbl->pde->proc_fops = &neigh_stat_seq_fops;
	tbl->pde->data = tbl;
#endif

	tbl->hash_mask = 1;
	tbl->hash_buckets = neigh_hash_alloc(tbl->hash_mask + 1);

	phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *);
A
Andrew Morton 已提交
1367
	tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL);
L
Linus Torvalds 已提交
1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383

	if (!tbl->hash_buckets || !tbl->phash_buckets)
		panic("cannot allocate neighbour cache hashes");

	get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd));

	rwlock_init(&tbl->lock);
	init_timer(&tbl->gc_timer);
	tbl->gc_timer.data     = (unsigned long)tbl;
	tbl->gc_timer.function = neigh_periodic_timer;
	tbl->gc_timer.expires  = now + 1;
	add_timer(&tbl->gc_timer);

	init_timer(&tbl->proxy_timer);
	tbl->proxy_timer.data	  = (unsigned long)tbl;
	tbl->proxy_timer.function = neigh_proxy_process;
1384 1385
	skb_queue_head_init_class(&tbl->proxy_queue,
			&neigh_table_proxy_queue_class);
L
Linus Torvalds 已提交
1386 1387 1388

	tbl->last_flush = now;
	tbl->last_rand	= now + tbl->parms.reachable_time * 20;
1389 1390 1391 1392 1393 1394 1395
}

void neigh_table_init(struct neigh_table *tbl)
{
	struct neigh_table *tmp;

	neigh_table_init_no_netlink(tbl);
L
Linus Torvalds 已提交
1396
	write_lock(&neigh_tbl_lock);
1397 1398 1399 1400
	for (tmp = neigh_tables; tmp; tmp = tmp->next) {
		if (tmp->family == tbl->family)
			break;
	}
L
Linus Torvalds 已提交
1401 1402 1403
	tbl->next	= neigh_tables;
	neigh_tables	= tbl;
	write_unlock(&neigh_tbl_lock);
1404 1405 1406 1407 1408 1409

	if (unlikely(tmp)) {
		printk(KERN_ERR "NEIGH: Registering multiple tables for "
		       "family %d\n", tbl->family);
		dump_stack();
	}
L
Linus Torvalds 已提交
1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437
}

int neigh_table_clear(struct neigh_table *tbl)
{
	struct neigh_table **tp;

	/* It is not clean... Fix it to unload IPv6 module safely */
	del_timer_sync(&tbl->gc_timer);
	del_timer_sync(&tbl->proxy_timer);
	pneigh_queue_purge(&tbl->proxy_queue);
	neigh_ifdown(tbl, NULL);
	if (atomic_read(&tbl->entries))
		printk(KERN_CRIT "neighbour leakage\n");
	write_lock(&neigh_tbl_lock);
	for (tp = &neigh_tables; *tp; tp = &(*tp)->next) {
		if (*tp == tbl) {
			*tp = tbl->next;
			break;
		}
	}
	write_unlock(&neigh_tbl_lock);

	neigh_hash_free(tbl->hash_buckets, tbl->hash_mask + 1);
	tbl->hash_buckets = NULL;

	kfree(tbl->phash_buckets);
	tbl->phash_buckets = NULL;

1438 1439 1440
	free_percpu(tbl->stats);
	tbl->stats = NULL;

L
Linus Torvalds 已提交
1441 1442 1443 1444 1445
	return 0;
}

int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
1446 1447
	struct ndmsg *ndm;
	struct nlattr *dst_attr;
L
Linus Torvalds 已提交
1448 1449
	struct neigh_table *tbl;
	struct net_device *dev = NULL;
1450
	int err = -EINVAL;
L
Linus Torvalds 已提交
1451

1452
	if (nlmsg_len(nlh) < sizeof(*ndm))
L
Linus Torvalds 已提交
1453 1454
		goto out;

1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467
	dst_attr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_DST);
	if (dst_attr == NULL)
		goto out;

	ndm = nlmsg_data(nlh);
	if (ndm->ndm_ifindex) {
		dev = dev_get_by_index(ndm->ndm_ifindex);
		if (dev == NULL) {
			err = -ENODEV;
			goto out;
		}
	}

L
Linus Torvalds 已提交
1468 1469
	read_lock(&neigh_tbl_lock);
	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
1470
		struct neighbour *neigh;
L
Linus Torvalds 已提交
1471 1472 1473 1474 1475

		if (tbl->family != ndm->ndm_family)
			continue;
		read_unlock(&neigh_tbl_lock);

1476
		if (nla_len(dst_attr) < tbl->key_len)
L
Linus Torvalds 已提交
1477 1478 1479
			goto out_dev_put;

		if (ndm->ndm_flags & NTF_PROXY) {
1480
			err = pneigh_delete(tbl, nla_data(dst_attr), dev);
L
Linus Torvalds 已提交
1481 1482 1483
			goto out_dev_put;
		}

1484 1485
		if (dev == NULL)
			goto out_dev_put;
L
Linus Torvalds 已提交
1486

1487 1488 1489 1490
		neigh = neigh_lookup(tbl, nla_data(dst_attr), dev);
		if (neigh == NULL) {
			err = -ENOENT;
			goto out_dev_put;
L
Linus Torvalds 已提交
1491
		}
1492 1493 1494 1495 1496

		err = neigh_update(neigh, NULL, NUD_FAILED,
				   NEIGH_UPDATE_F_OVERRIDE |
				   NEIGH_UPDATE_F_ADMIN);
		neigh_release(neigh);
L
Linus Torvalds 已提交
1497 1498 1499
		goto out_dev_put;
	}
	read_unlock(&neigh_tbl_lock);
1500 1501
	err = -EAFNOSUPPORT;

L
Linus Torvalds 已提交
1502 1503 1504 1505 1506 1507 1508 1509 1510
out_dev_put:
	if (dev)
		dev_put(dev);
out:
	return err;
}

int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
1511 1512
	struct ndmsg *ndm;
	struct nlattr *tb[NDA_MAX+1];
L
Linus Torvalds 已提交
1513 1514
	struct neigh_table *tbl;
	struct net_device *dev = NULL;
1515
	int err;
L
Linus Torvalds 已提交
1516

1517 1518
	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
	if (err < 0)
L
Linus Torvalds 已提交
1519 1520
		goto out;

1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536
	err = -EINVAL;
	if (tb[NDA_DST] == NULL)
		goto out;

	ndm = nlmsg_data(nlh);
	if (ndm->ndm_ifindex) {
		dev = dev_get_by_index(ndm->ndm_ifindex);
		if (dev == NULL) {
			err = -ENODEV;
			goto out;
		}

		if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len)
			goto out_dev_put;
	}

L
Linus Torvalds 已提交
1537 1538
	read_lock(&neigh_tbl_lock);
	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
1539 1540 1541
		int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
		struct neighbour *neigh;
		void *dst, *lladdr;
L
Linus Torvalds 已提交
1542 1543 1544 1545 1546

		if (tbl->family != ndm->ndm_family)
			continue;
		read_unlock(&neigh_tbl_lock);

1547
		if (nla_len(tb[NDA_DST]) < tbl->key_len)
L
Linus Torvalds 已提交
1548
			goto out_dev_put;
1549 1550
		dst = nla_data(tb[NDA_DST]);
		lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
L
Linus Torvalds 已提交
1551 1552

		if (ndm->ndm_flags & NTF_PROXY) {
1553 1554 1555 1556 1557 1558 1559 1560
			struct pneigh_entry *pn;

			err = -ENOBUFS;
			pn = pneigh_lookup(tbl, dst, dev, 1);
			if (pn) {
				pn->flags = ndm->ndm_flags;
				err = 0;
			}
L
Linus Torvalds 已提交
1561 1562 1563
			goto out_dev_put;
		}

1564
		if (dev == NULL)
L
Linus Torvalds 已提交
1565
			goto out_dev_put;
1566 1567 1568 1569 1570 1571 1572

		neigh = neigh_lookup(tbl, dst, dev);
		if (neigh == NULL) {
			if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
				err = -ENOENT;
				goto out_dev_put;
			}
1573

1574 1575 1576
			neigh = __neigh_lookup_errno(tbl, dst, dev);
			if (IS_ERR(neigh)) {
				err = PTR_ERR(neigh);
L
Linus Torvalds 已提交
1577 1578 1579
				goto out_dev_put;
			}
		} else {
1580 1581 1582
			if (nlh->nlmsg_flags & NLM_F_EXCL) {
				err = -EEXIST;
				neigh_release(neigh);
L
Linus Torvalds 已提交
1583 1584 1585
				goto out_dev_put;
			}

1586 1587 1588
			if (!(nlh->nlmsg_flags & NLM_F_REPLACE))
				flags &= ~NEIGH_UPDATE_F_OVERRIDE;
		}
L
Linus Torvalds 已提交
1589

1590 1591
		err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
		neigh_release(neigh);
L
Linus Torvalds 已提交
1592 1593 1594 1595
		goto out_dev_put;
	}

	read_unlock(&neigh_tbl_lock);
1596 1597
	err = -EAFNOSUPPORT;

L
Linus Torvalds 已提交
1598 1599 1600 1601 1602 1603 1604
out_dev_put:
	if (dev)
		dev_put(dev);
out:
	return err;
}

1605 1606
static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
{
1607 1608 1609 1610 1611
	struct nlattr *nest;

	nest = nla_nest_start(skb, NDTA_PARMS);
	if (nest == NULL)
		return -ENOBUFS;
1612 1613

	if (parms->dev)
1614 1615 1616 1617 1618 1619 1620 1621 1622 1623
		NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex);

	NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt));
	NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len);
	NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen);
	NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes);
	NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes);
	NLA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes);
	NLA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time);
	NLA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME,
1624
		      parms->base_reachable_time);
1625 1626 1627 1628 1629 1630
	NLA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime);
	NLA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time);
	NLA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time);
	NLA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay);
	NLA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay);
	NLA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime);
1631

1632
	return nla_nest_end(skb, nest);
1633

1634 1635
nla_put_failure:
	return nla_nest_cancel(skb, nest);
1636 1637
}

1638 1639
static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
			      u32 pid, u32 seq, int type, int flags)
1640 1641 1642 1643
{
	struct nlmsghdr *nlh;
	struct ndtmsg *ndtmsg;

1644 1645
	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags);
	if (nlh == NULL)
1646
		return -EMSGSIZE;
1647

1648
	ndtmsg = nlmsg_data(nlh);
1649 1650 1651

	read_lock_bh(&tbl->lock);
	ndtmsg->ndtm_family = tbl->family;
1652 1653
	ndtmsg->ndtm_pad1   = 0;
	ndtmsg->ndtm_pad2   = 0;
1654

1655 1656 1657 1658 1659
	NLA_PUT_STRING(skb, NDTA_NAME, tbl->id);
	NLA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval);
	NLA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1);
	NLA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2);
	NLA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3);
1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677

	{
		unsigned long now = jiffies;
		unsigned int flush_delta = now - tbl->last_flush;
		unsigned int rand_delta = now - tbl->last_rand;

		struct ndt_config ndc = {
			.ndtc_key_len		= tbl->key_len,
			.ndtc_entry_size	= tbl->entry_size,
			.ndtc_entries		= atomic_read(&tbl->entries),
			.ndtc_last_flush	= jiffies_to_msecs(flush_delta),
			.ndtc_last_rand		= jiffies_to_msecs(rand_delta),
			.ndtc_hash_rnd		= tbl->hash_rnd,
			.ndtc_hash_mask		= tbl->hash_mask,
			.ndtc_hash_chain_gc	= tbl->hash_chain_gc,
			.ndtc_proxy_qlen	= tbl->proxy_queue.qlen,
		};

1678
		NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc);
1679 1680 1681 1682 1683 1684 1685 1686
	}

	{
		int cpu;
		struct ndt_stats ndst;

		memset(&ndst, 0, sizeof(ndst));

1687
		for_each_possible_cpu(cpu) {
1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702
			struct neigh_statistics	*st;

			st = per_cpu_ptr(tbl->stats, cpu);
			ndst.ndts_allocs		+= st->allocs;
			ndst.ndts_destroys		+= st->destroys;
			ndst.ndts_hash_grows		+= st->hash_grows;
			ndst.ndts_res_failed		+= st->res_failed;
			ndst.ndts_lookups		+= st->lookups;
			ndst.ndts_hits			+= st->hits;
			ndst.ndts_rcv_probes_mcast	+= st->rcv_probes_mcast;
			ndst.ndts_rcv_probes_ucast	+= st->rcv_probes_ucast;
			ndst.ndts_periodic_gc_runs	+= st->periodic_gc_runs;
			ndst.ndts_forced_gc_runs	+= st->forced_gc_runs;
		}

1703
		NLA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst);
1704 1705 1706 1707
	}

	BUG_ON(tbl->parms.dev);
	if (neightbl_fill_parms(skb, &tbl->parms) < 0)
1708
		goto nla_put_failure;
1709 1710

	read_unlock_bh(&tbl->lock);
1711
	return nlmsg_end(skb, nlh);
1712

1713
nla_put_failure:
1714
	read_unlock_bh(&tbl->lock);
1715 1716
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
1717 1718
}

1719 1720
static int neightbl_fill_param_info(struct sk_buff *skb,
				    struct neigh_table *tbl,
1721
				    struct neigh_parms *parms,
1722 1723
				    u32 pid, u32 seq, int type,
				    unsigned int flags)
1724 1725 1726 1727
{
	struct ndtmsg *ndtmsg;
	struct nlmsghdr *nlh;

1728 1729
	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags);
	if (nlh == NULL)
1730
		return -EMSGSIZE;
1731

1732
	ndtmsg = nlmsg_data(nlh);
1733 1734 1735

	read_lock_bh(&tbl->lock);
	ndtmsg->ndtm_family = tbl->family;
1736 1737
	ndtmsg->ndtm_pad1   = 0;
	ndtmsg->ndtm_pad2   = 0;
1738

1739 1740 1741
	if (nla_put_string(skb, NDTA_NAME, tbl->id) < 0 ||
	    neightbl_fill_parms(skb, parms) < 0)
		goto errout;
1742 1743

	read_unlock_bh(&tbl->lock);
1744 1745
	return nlmsg_end(skb, nlh);
errout:
1746
	read_unlock_bh(&tbl->lock);
1747 1748
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
1749
}
1750

1751 1752 1753 1754
static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl,
						      int ifindex)
{
	struct neigh_parms *p;
1755

1756 1757 1758 1759 1760 1761 1762 1763
	for (p = &tbl->parms; p; p = p->next)
		if ((p->dev && p->dev->ifindex == ifindex) ||
		    (!p->dev && !ifindex))
			return p;

	return NULL;
}

1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788
static struct nla_policy nl_neightbl_policy[NDTA_MAX+1] __read_mostly = {
	[NDTA_NAME]		= { .type = NLA_STRING },
	[NDTA_THRESH1]		= { .type = NLA_U32 },
	[NDTA_THRESH2]		= { .type = NLA_U32 },
	[NDTA_THRESH3]		= { .type = NLA_U32 },
	[NDTA_GC_INTERVAL]	= { .type = NLA_U64 },
	[NDTA_PARMS]		= { .type = NLA_NESTED },
};

static struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] __read_mostly = {
	[NDTPA_IFINDEX]			= { .type = NLA_U32 },
	[NDTPA_QUEUE_LEN]		= { .type = NLA_U32 },
	[NDTPA_PROXY_QLEN]		= { .type = NLA_U32 },
	[NDTPA_APP_PROBES]		= { .type = NLA_U32 },
	[NDTPA_UCAST_PROBES]		= { .type = NLA_U32 },
	[NDTPA_MCAST_PROBES]		= { .type = NLA_U32 },
	[NDTPA_BASE_REACHABLE_TIME]	= { .type = NLA_U64 },
	[NDTPA_GC_STALETIME]		= { .type = NLA_U64 },
	[NDTPA_DELAY_PROBE_TIME]	= { .type = NLA_U64 },
	[NDTPA_RETRANS_TIME]		= { .type = NLA_U64 },
	[NDTPA_ANYCAST_DELAY]		= { .type = NLA_U64 },
	[NDTPA_PROXY_DELAY]		= { .type = NLA_U64 },
	[NDTPA_LOCKTIME]		= { .type = NLA_U64 },
};

1789 1790 1791
int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct neigh_table *tbl;
1792 1793 1794
	struct ndtmsg *ndtmsg;
	struct nlattr *tb[NDTA_MAX+1];
	int err;
1795

1796 1797 1798 1799
	err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX,
			  nl_neightbl_policy);
	if (err < 0)
		goto errout;
1800

1801 1802 1803 1804 1805 1806
	if (tb[NDTA_NAME] == NULL) {
		err = -EINVAL;
		goto errout;
	}

	ndtmsg = nlmsg_data(nlh);
1807 1808 1809 1810 1811
	read_lock(&neigh_tbl_lock);
	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
		if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family)
			continue;

1812
		if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0)
1813 1814 1815 1816 1817
			break;
	}

	if (tbl == NULL) {
		err = -ENOENT;
1818
		goto errout_locked;
1819 1820
	}

1821
	/*
1822 1823 1824 1825 1826
	 * We acquire tbl->lock to be nice to the periodic timers and
	 * make sure they always see a consistent set of values.
	 */
	write_lock_bh(&tbl->lock);

1827 1828
	if (tb[NDTA_PARMS]) {
		struct nlattr *tbp[NDTPA_MAX+1];
1829
		struct neigh_parms *p;
1830
		int i, ifindex = 0;
1831

1832 1833 1834 1835
		err = nla_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS],
				       nl_ntbl_parm_policy);
		if (err < 0)
			goto errout_tbl_lock;
1836

1837 1838
		if (tbp[NDTPA_IFINDEX])
			ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]);
1839 1840 1841 1842

		p = lookup_neigh_params(tbl, ifindex);
		if (p == NULL) {
			err = -ENOENT;
1843
			goto errout_tbl_lock;
1844 1845
		}

1846 1847 1848
		for (i = 1; i <= NDTPA_MAX; i++) {
			if (tbp[i] == NULL)
				continue;
1849

1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889
			switch (i) {
			case NDTPA_QUEUE_LEN:
				p->queue_len = nla_get_u32(tbp[i]);
				break;
			case NDTPA_PROXY_QLEN:
				p->proxy_qlen = nla_get_u32(tbp[i]);
				break;
			case NDTPA_APP_PROBES:
				p->app_probes = nla_get_u32(tbp[i]);
				break;
			case NDTPA_UCAST_PROBES:
				p->ucast_probes = nla_get_u32(tbp[i]);
				break;
			case NDTPA_MCAST_PROBES:
				p->mcast_probes = nla_get_u32(tbp[i]);
				break;
			case NDTPA_BASE_REACHABLE_TIME:
				p->base_reachable_time = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_GC_STALETIME:
				p->gc_staletime = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_DELAY_PROBE_TIME:
				p->delay_probe_time = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_RETRANS_TIME:
				p->retrans_time = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_ANYCAST_DELAY:
				p->anycast_delay = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_PROXY_DELAY:
				p->proxy_delay = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_LOCKTIME:
				p->locktime = nla_get_msecs(tbp[i]);
				break;
			}
		}
	}
1890

1891 1892
	if (tb[NDTA_THRESH1])
		tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]);
1893

1894 1895
	if (tb[NDTA_THRESH2])
		tbl->gc_thresh2 = nla_get_u32(tb[NDTA_THRESH2]);
1896

1897 1898
	if (tb[NDTA_THRESH3])
		tbl->gc_thresh3 = nla_get_u32(tb[NDTA_THRESH3]);
1899

1900 1901
	if (tb[NDTA_GC_INTERVAL])
		tbl->gc_interval = nla_get_msecs(tb[NDTA_GC_INTERVAL]);
1902 1903 1904

	err = 0;

1905
errout_tbl_lock:
1906
	write_unlock_bh(&tbl->lock);
1907
errout_locked:
1908
	read_unlock(&neigh_tbl_lock);
1909
errout:
1910 1911 1912 1913 1914
	return err;
}

int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
{
1915 1916 1917
	int family, tidx, nidx = 0;
	int tbl_skip = cb->args[0];
	int neigh_skip = cb->args[1];
1918 1919
	struct neigh_table *tbl;

1920
	family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
1921 1922

	read_lock(&neigh_tbl_lock);
1923
	for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) {
1924 1925
		struct neigh_parms *p;

1926
		if (tidx < tbl_skip || (family && tbl->family != family))
1927 1928
			continue;

1929 1930 1931
		if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).pid,
				       cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL,
				       NLM_F_MULTI) <= 0)
1932 1933
			break;

1934 1935
		for (nidx = 0, p = tbl->parms.next; p; p = p->next, nidx++) {
			if (nidx < neigh_skip)
1936 1937
				continue;

1938 1939 1940 1941 1942
			if (neightbl_fill_param_info(skb, tbl, p,
						     NETLINK_CB(cb->skb).pid,
						     cb->nlh->nlmsg_seq,
						     RTM_NEWNEIGHTBL,
						     NLM_F_MULTI) <= 0)
1943 1944 1945
				goto out;
		}

1946
		neigh_skip = 0;
1947 1948 1949
	}
out:
	read_unlock(&neigh_tbl_lock);
1950 1951
	cb->args[0] = tidx;
	cb->args[1] = nidx;
1952 1953 1954

	return skb->len;
}
L
Linus Torvalds 已提交
1955

1956 1957
static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
			   u32 pid, u32 seq, int type, unsigned int flags)
L
Linus Torvalds 已提交
1958 1959 1960
{
	unsigned long now = jiffies;
	struct nda_cacheinfo ci;
1961 1962 1963 1964 1965
	struct nlmsghdr *nlh;
	struct ndmsg *ndm;

	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags);
	if (nlh == NULL)
1966
		return -EMSGSIZE;
L
Linus Torvalds 已提交
1967

1968 1969
	ndm = nlmsg_data(nlh);
	ndm->ndm_family	 = neigh->ops->family;
1970 1971
	ndm->ndm_pad1    = 0;
	ndm->ndm_pad2    = 0;
1972 1973 1974
	ndm->ndm_flags	 = neigh->flags;
	ndm->ndm_type	 = neigh->type;
	ndm->ndm_ifindex = neigh->dev->ifindex;
L
Linus Torvalds 已提交
1975

1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997
	NLA_PUT(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key);

	read_lock_bh(&neigh->lock);
	ndm->ndm_state	 = neigh->nud_state;
	if ((neigh->nud_state & NUD_VALID) &&
	    nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, neigh->ha) < 0) {
		read_unlock_bh(&neigh->lock);
		goto nla_put_failure;
	}

	ci.ndm_used	 = now - neigh->used;
	ci.ndm_confirmed = now - neigh->confirmed;
	ci.ndm_updated	 = now - neigh->updated;
	ci.ndm_refcnt	 = atomic_read(&neigh->refcnt) - 1;
	read_unlock_bh(&neigh->lock);

	NLA_PUT_U32(skb, NDA_PROBES, atomic_read(&neigh->probes));
	NLA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci);

	return nlmsg_end(skb, nlh);

nla_put_failure:
1998 1999
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
L
Linus Torvalds 已提交
2000 2001 2002 2003 2004 2005 2006 2007 2008 2009
}


static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
			    struct netlink_callback *cb)
{
	struct neighbour *n;
	int rc, h, s_h = cb->args[1];
	int idx, s_idx = idx = cb->args[2];

2010
	read_lock_bh(&tbl->lock);
L
Linus Torvalds 已提交
2011 2012 2013 2014 2015 2016 2017 2018 2019 2020
	for (h = 0; h <= tbl->hash_mask; h++) {
		if (h < s_h)
			continue;
		if (h > s_h)
			s_idx = 0;
		for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next, idx++) {
			if (idx < s_idx)
				continue;
			if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid,
					    cb->nlh->nlmsg_seq,
2021 2022
					    RTM_NEWNEIGH,
					    NLM_F_MULTI) <= 0) {
L
Linus Torvalds 已提交
2023 2024 2025 2026 2027 2028
				read_unlock_bh(&tbl->lock);
				rc = -1;
				goto out;
			}
		}
	}
2029
	read_unlock_bh(&tbl->lock);
L
Linus Torvalds 已提交
2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042
	rc = skb->len;
out:
	cb->args[1] = h;
	cb->args[2] = idx;
	return rc;
}

int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct neigh_table *tbl;
	int t, family, s_t;

	read_lock(&neigh_tbl_lock);
2043
	family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
L
Linus Torvalds 已提交
2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096
	s_t = cb->args[0];

	for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) {
		if (t < s_t || (family && tbl->family != family))
			continue;
		if (t > s_t)
			memset(&cb->args[1], 0, sizeof(cb->args) -
						sizeof(cb->args[0]));
		if (neigh_dump_table(tbl, skb, cb) < 0)
			break;
	}
	read_unlock(&neigh_tbl_lock);

	cb->args[0] = t;
	return skb->len;
}

void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie)
{
	int chain;

	read_lock_bh(&tbl->lock);
	for (chain = 0; chain <= tbl->hash_mask; chain++) {
		struct neighbour *n;

		for (n = tbl->hash_buckets[chain]; n; n = n->next)
			cb(n, cookie);
	}
	read_unlock_bh(&tbl->lock);
}
EXPORT_SYMBOL(neigh_for_each);

/* The tbl->lock must be held as a writer and BH disabled. */
void __neigh_for_each_release(struct neigh_table *tbl,
			      int (*cb)(struct neighbour *))
{
	int chain;

	for (chain = 0; chain <= tbl->hash_mask; chain++) {
		struct neighbour *n, **np;

		np = &tbl->hash_buckets[chain];
		while ((n = *np) != NULL) {
			int release;

			write_lock(&n->lock);
			release = cb(n);
			if (release) {
				*np = n->next;
				n->dead = 1;
			} else
				np = &n->next;
			write_unlock(&n->lock);
2097 2098 2099
			if (release) {
				if (n->parms->neigh_cleanup)
					n->parms->neigh_cleanup(n);
L
Linus Torvalds 已提交
2100
				neigh_release(n);
2101
			}
L
Linus Torvalds 已提交
2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331
		}
	}
}
EXPORT_SYMBOL(__neigh_for_each_release);

#ifdef CONFIG_PROC_FS

static struct neighbour *neigh_get_first(struct seq_file *seq)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;
	struct neighbour *n = NULL;
	int bucket = state->bucket;

	state->flags &= ~NEIGH_SEQ_IS_PNEIGH;
	for (bucket = 0; bucket <= tbl->hash_mask; bucket++) {
		n = tbl->hash_buckets[bucket];

		while (n) {
			if (state->neigh_sub_iter) {
				loff_t fakep = 0;
				void *v;

				v = state->neigh_sub_iter(state, n, &fakep);
				if (!v)
					goto next;
			}
			if (!(state->flags & NEIGH_SEQ_SKIP_NOARP))
				break;
			if (n->nud_state & ~NUD_NOARP)
				break;
		next:
			n = n->next;
		}

		if (n)
			break;
	}
	state->bucket = bucket;

	return n;
}

static struct neighbour *neigh_get_next(struct seq_file *seq,
					struct neighbour *n,
					loff_t *pos)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;

	if (state->neigh_sub_iter) {
		void *v = state->neigh_sub_iter(state, n, pos);
		if (v)
			return n;
	}
	n = n->next;

	while (1) {
		while (n) {
			if (state->neigh_sub_iter) {
				void *v = state->neigh_sub_iter(state, n, pos);
				if (v)
					return n;
				goto next;
			}
			if (!(state->flags & NEIGH_SEQ_SKIP_NOARP))
				break;

			if (n->nud_state & ~NUD_NOARP)
				break;
		next:
			n = n->next;
		}

		if (n)
			break;

		if (++state->bucket > tbl->hash_mask)
			break;

		n = tbl->hash_buckets[state->bucket];
	}

	if (n && pos)
		--(*pos);
	return n;
}

static struct neighbour *neigh_get_idx(struct seq_file *seq, loff_t *pos)
{
	struct neighbour *n = neigh_get_first(seq);

	if (n) {
		while (*pos) {
			n = neigh_get_next(seq, n, pos);
			if (!n)
				break;
		}
	}
	return *pos ? NULL : n;
}

static struct pneigh_entry *pneigh_get_first(struct seq_file *seq)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;
	struct pneigh_entry *pn = NULL;
	int bucket = state->bucket;

	state->flags |= NEIGH_SEQ_IS_PNEIGH;
	for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) {
		pn = tbl->phash_buckets[bucket];
		if (pn)
			break;
	}
	state->bucket = bucket;

	return pn;
}

static struct pneigh_entry *pneigh_get_next(struct seq_file *seq,
					    struct pneigh_entry *pn,
					    loff_t *pos)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;

	pn = pn->next;
	while (!pn) {
		if (++state->bucket > PNEIGH_HASHMASK)
			break;
		pn = tbl->phash_buckets[state->bucket];
		if (pn)
			break;
	}

	if (pn && pos)
		--(*pos);

	return pn;
}

static struct pneigh_entry *pneigh_get_idx(struct seq_file *seq, loff_t *pos)
{
	struct pneigh_entry *pn = pneigh_get_first(seq);

	if (pn) {
		while (*pos) {
			pn = pneigh_get_next(seq, pn, pos);
			if (!pn)
				break;
		}
	}
	return *pos ? NULL : pn;
}

static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos)
{
	struct neigh_seq_state *state = seq->private;
	void *rc;

	rc = neigh_get_idx(seq, pos);
	if (!rc && !(state->flags & NEIGH_SEQ_NEIGH_ONLY))
		rc = pneigh_get_idx(seq, pos);

	return rc;
}

void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags)
{
	struct neigh_seq_state *state = seq->private;
	loff_t pos_minus_one;

	state->tbl = tbl;
	state->bucket = 0;
	state->flags = (neigh_seq_flags & ~NEIGH_SEQ_IS_PNEIGH);

	read_lock_bh(&tbl->lock);

	pos_minus_one = *pos - 1;
	return *pos ? neigh_get_idx_any(seq, &pos_minus_one) : SEQ_START_TOKEN;
}
EXPORT_SYMBOL(neigh_seq_start);

void *neigh_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct neigh_seq_state *state;
	void *rc;

	if (v == SEQ_START_TOKEN) {
		rc = neigh_get_idx(seq, pos);
		goto out;
	}

	state = seq->private;
	if (!(state->flags & NEIGH_SEQ_IS_PNEIGH)) {
		rc = neigh_get_next(seq, v, NULL);
		if (rc)
			goto out;
		if (!(state->flags & NEIGH_SEQ_NEIGH_ONLY))
			rc = pneigh_get_first(seq);
	} else {
		BUG_ON(state->flags & NEIGH_SEQ_NEIGH_ONLY);
		rc = pneigh_get_next(seq, v, NULL);
	}
out:
	++(*pos);
	return rc;
}
EXPORT_SYMBOL(neigh_seq_next);

void neigh_seq_stop(struct seq_file *seq, void *v)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;

	read_unlock_bh(&tbl->lock);
}
EXPORT_SYMBOL(neigh_seq_stop);

/* statistics via seq_file */

static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct proc_dir_entry *pde = seq->private;
	struct neigh_table *tbl = pde->data;
	int cpu;

	if (*pos == 0)
		return SEQ_START_TOKEN;
2332

L
Linus Torvalds 已提交
2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368
	for (cpu = *pos-1; cpu < NR_CPUS; ++cpu) {
		if (!cpu_possible(cpu))
			continue;
		*pos = cpu+1;
		return per_cpu_ptr(tbl->stats, cpu);
	}
	return NULL;
}

static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct proc_dir_entry *pde = seq->private;
	struct neigh_table *tbl = pde->data;
	int cpu;

	for (cpu = *pos; cpu < NR_CPUS; ++cpu) {
		if (!cpu_possible(cpu))
			continue;
		*pos = cpu+1;
		return per_cpu_ptr(tbl->stats, cpu);
	}
	return NULL;
}

static void neigh_stat_seq_stop(struct seq_file *seq, void *v)
{

}

static int neigh_stat_seq_show(struct seq_file *seq, void *v)
{
	struct proc_dir_entry *pde = seq->private;
	struct neigh_table *tbl = pde->data;
	struct neigh_statistics *st = v;

	if (v == SEQ_START_TOKEN) {
2369
		seq_printf(seq, "entries  allocs destroys hash_grows  lookups hits  res_failed  rcv_probes_mcast rcv_probes_ucast  periodic_gc_runs forced_gc_runs\n");
L
Linus Torvalds 已提交
2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413
		return 0;
	}

	seq_printf(seq, "%08x  %08lx %08lx %08lx  %08lx %08lx  %08lx  "
			"%08lx %08lx  %08lx %08lx\n",
		   atomic_read(&tbl->entries),

		   st->allocs,
		   st->destroys,
		   st->hash_grows,

		   st->lookups,
		   st->hits,

		   st->res_failed,

		   st->rcv_probes_mcast,
		   st->rcv_probes_ucast,

		   st->periodic_gc_runs,
		   st->forced_gc_runs
		   );

	return 0;
}

static struct seq_operations neigh_stat_seq_ops = {
	.start	= neigh_stat_seq_start,
	.next	= neigh_stat_seq_next,
	.stop	= neigh_stat_seq_stop,
	.show	= neigh_stat_seq_show,
};

static int neigh_stat_seq_open(struct inode *inode, struct file *file)
{
	int ret = seq_open(file, &neigh_stat_seq_ops);

	if (!ret) {
		struct seq_file *sf = file->private_data;
		sf->private = PDE(inode);
	}
	return ret;
};

2414
static const struct file_operations neigh_stat_seq_fops = {
L
Linus Torvalds 已提交
2415 2416 2417 2418 2419 2420 2421 2422 2423 2424
	.owner	 = THIS_MODULE,
	.open 	 = neigh_stat_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release,
};

#endif /* CONFIG_PROC_FS */

#ifdef CONFIG_ARPD
2425 2426 2427 2428 2429 2430 2431 2432 2433
static inline size_t neigh_nlmsg_size(void)
{
	return NLMSG_ALIGN(sizeof(struct ndmsg))
	       + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */
	       + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */
	       + nla_total_size(sizeof(struct nda_cacheinfo))
	       + nla_total_size(4); /* NDA_PROBES */
}

2434
static void __neigh_notify(struct neighbour *n, int type, int flags)
L
Linus Torvalds 已提交
2435
{
2436
	struct sk_buff *skb;
2437
	int err = -ENOBUFS;
L
Linus Torvalds 已提交
2438

2439
	skb = nlmsg_new(neigh_nlmsg_size(), GFP_ATOMIC);
2440
	if (skb == NULL)
2441
		goto errout;
L
Linus Torvalds 已提交
2442

2443
	err = neigh_fill_info(skb, n, 0, 0, type, flags);
2444 2445 2446 2447 2448 2449
	if (err < 0) {
		/* -EMSGSIZE implies BUG in neigh_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}
2450 2451 2452 2453
	err = rtnl_notify(skb, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
errout:
	if (err < 0)
		rtnl_set_sk_err(RTNLGRP_NEIGH, err);
L
Linus Torvalds 已提交
2454 2455
}

2456
void neigh_app_ns(struct neighbour *n)
L
Linus Torvalds 已提交
2457
{
2458 2459
	__neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST);
}
L
Linus Torvalds 已提交
2460

2461 2462 2463
static void neigh_app_notify(struct neighbour *n)
{
	__neigh_notify(n, RTM_NEWNEIGH, 0);
L
Linus Torvalds 已提交
2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476
}

#endif /* CONFIG_ARPD */

#ifdef CONFIG_SYSCTL

static struct neigh_sysctl_table {
	struct ctl_table_header *sysctl_header;
	ctl_table		neigh_vars[__NET_NEIGH_MAX];
	ctl_table		neigh_dev[2];
	ctl_table		neigh_neigh_dir[2];
	ctl_table		neigh_proto_dir[2];
	ctl_table		neigh_root_dir[2];
2477
} neigh_sysctl_template __read_mostly = {
L
Linus Torvalds 已提交
2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639
	.neigh_vars = {
		{
			.ctl_name	= NET_NEIGH_MCAST_SOLICIT,
			.procname	= "mcast_solicit",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_UCAST_SOLICIT,
			.procname	= "ucast_solicit",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_APP_SOLICIT,
			.procname	= "app_solicit",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_RETRANS_TIME,
			.procname	= "retrans_time",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_userhz_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_REACHABLE_TIME,
			.procname	= "base_reachable_time",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_jiffies,
			.strategy	= &sysctl_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_DELAY_PROBE_TIME,
			.procname	= "delay_first_probe_time",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_jiffies,
			.strategy	= &sysctl_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_GC_STALE_TIME,
			.procname	= "gc_stale_time",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_jiffies,
			.strategy	= &sysctl_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_UNRES_QLEN,
			.procname	= "unres_qlen",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_PROXY_QLEN,
			.procname	= "proxy_qlen",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_ANYCAST_DELAY,
			.procname	= "anycast_delay",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_userhz_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_PROXY_DELAY,
			.procname	= "proxy_delay",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_userhz_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_LOCKTIME,
			.procname	= "locktime",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_userhz_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_GC_INTERVAL,
			.procname	= "gc_interval",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_jiffies,
			.strategy	= &sysctl_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_GC_THRESH1,
			.procname	= "gc_thresh1",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_GC_THRESH2,
			.procname	= "gc_thresh2",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_GC_THRESH3,
			.procname	= "gc_thresh3",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_RETRANS_TIME_MS,
			.procname	= "retrans_time_ms",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_ms_jiffies,
			.strategy	= &sysctl_ms_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_REACHABLE_TIME_MS,
			.procname	= "base_reachable_time_ms",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_ms_jiffies,
			.strategy	= &sysctl_ms_jiffies,
		},
	},
	.neigh_dev = {
		{
			.ctl_name	= NET_PROTO_CONF_DEFAULT,
			.procname	= "default",
			.mode		= 0555,
		},
	},
	.neigh_neigh_dir = {
		{
			.procname	= "neigh",
			.mode		= 0555,
		},
	},
	.neigh_proto_dir = {
		{
			.mode		= 0555,
		},
	},
	.neigh_root_dir = {
		{
			.ctl_name	= CTL_NET,
			.procname	= "net",
			.mode		= 0555,
		},
	},
};

int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
2640
			  int p_id, int pdev_id, char *p_name,
L
Linus Torvalds 已提交
2641 2642
			  proc_handler *handler, ctl_handler *strategy)
{
2643 2644
	struct neigh_sysctl_table *t = kmemdup(&neigh_sysctl_template,
					       sizeof(*t), GFP_KERNEL);
L
Linus Torvalds 已提交
2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671
	const char *dev_name_source = NULL;
	char *dev_name = NULL;
	int err = 0;

	if (!t)
		return -ENOBUFS;
	t->neigh_vars[0].data  = &p->mcast_probes;
	t->neigh_vars[1].data  = &p->ucast_probes;
	t->neigh_vars[2].data  = &p->app_probes;
	t->neigh_vars[3].data  = &p->retrans_time;
	t->neigh_vars[4].data  = &p->base_reachable_time;
	t->neigh_vars[5].data  = &p->delay_probe_time;
	t->neigh_vars[6].data  = &p->gc_staletime;
	t->neigh_vars[7].data  = &p->queue_len;
	t->neigh_vars[8].data  = &p->proxy_qlen;
	t->neigh_vars[9].data  = &p->anycast_delay;
	t->neigh_vars[10].data = &p->proxy_delay;
	t->neigh_vars[11].data = &p->locktime;

	if (dev) {
		dev_name_source = dev->name;
		t->neigh_dev[0].ctl_name = dev->ifindex;
		t->neigh_vars[12].procname = NULL;
		t->neigh_vars[13].procname = NULL;
		t->neigh_vars[14].procname = NULL;
		t->neigh_vars[15].procname = NULL;
	} else {
2672
		dev_name_source = t->neigh_dev[0].procname;
L
Linus Torvalds 已提交
2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700
		t->neigh_vars[12].data = (int *)(p + 1);
		t->neigh_vars[13].data = (int *)(p + 1) + 1;
		t->neigh_vars[14].data = (int *)(p + 1) + 2;
		t->neigh_vars[15].data = (int *)(p + 1) + 3;
	}

	t->neigh_vars[16].data  = &p->retrans_time;
	t->neigh_vars[17].data  = &p->base_reachable_time;

	if (handler || strategy) {
		/* RetransTime */
		t->neigh_vars[3].proc_handler = handler;
		t->neigh_vars[3].strategy = strategy;
		t->neigh_vars[3].extra1 = dev;
		/* ReachableTime */
		t->neigh_vars[4].proc_handler = handler;
		t->neigh_vars[4].strategy = strategy;
		t->neigh_vars[4].extra1 = dev;
		/* RetransTime (in milliseconds)*/
		t->neigh_vars[16].proc_handler = handler;
		t->neigh_vars[16].strategy = strategy;
		t->neigh_vars[16].extra1 = dev;
		/* ReachableTime (in milliseconds) */
		t->neigh_vars[17].proc_handler = handler;
		t->neigh_vars[17].strategy = strategy;
		t->neigh_vars[17].extra1 = dev;
	}

2701
	dev_name = kstrdup(dev_name_source, GFP_KERNEL);
L
Linus Torvalds 已提交
2702 2703 2704 2705 2706
	if (!dev_name) {
		err = -ENOBUFS;
		goto free;
	}

2707
	t->neigh_dev[0].procname = dev_name;
L
Linus Torvalds 已提交
2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718

	t->neigh_neigh_dir[0].ctl_name = pdev_id;

	t->neigh_proto_dir[0].procname = p_name;
	t->neigh_proto_dir[0].ctl_name = p_id;

	t->neigh_dev[0].child	       = t->neigh_vars;
	t->neigh_neigh_dir[0].child    = t->neigh_dev;
	t->neigh_proto_dir[0].child    = t->neigh_neigh_dir;
	t->neigh_root_dir[0].child     = t->neigh_proto_dir;

2719
	t->sysctl_header = register_sysctl_table(t->neigh_root_dir);
L
Linus Torvalds 已提交
2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766
	if (!t->sysctl_header) {
		err = -ENOBUFS;
		goto free_procname;
	}
	p->sysctl_table = t;
	return 0;

	/* error path */
 free_procname:
	kfree(dev_name);
 free:
	kfree(t);

	return err;
}

void neigh_sysctl_unregister(struct neigh_parms *p)
{
	if (p->sysctl_table) {
		struct neigh_sysctl_table *t = p->sysctl_table;
		p->sysctl_table = NULL;
		unregister_sysctl_table(t->sysctl_header);
		kfree(t->neigh_dev[0].procname);
		kfree(t);
	}
}

#endif	/* CONFIG_SYSCTL */

EXPORT_SYMBOL(__neigh_event_send);
EXPORT_SYMBOL(neigh_changeaddr);
EXPORT_SYMBOL(neigh_compat_output);
EXPORT_SYMBOL(neigh_connected_output);
EXPORT_SYMBOL(neigh_create);
EXPORT_SYMBOL(neigh_delete);
EXPORT_SYMBOL(neigh_destroy);
EXPORT_SYMBOL(neigh_dump_info);
EXPORT_SYMBOL(neigh_event_ns);
EXPORT_SYMBOL(neigh_ifdown);
EXPORT_SYMBOL(neigh_lookup);
EXPORT_SYMBOL(neigh_lookup_nodev);
EXPORT_SYMBOL(neigh_parms_alloc);
EXPORT_SYMBOL(neigh_parms_release);
EXPORT_SYMBOL(neigh_rand_reach_time);
EXPORT_SYMBOL(neigh_resolve_output);
EXPORT_SYMBOL(neigh_table_clear);
EXPORT_SYMBOL(neigh_table_init);
2767
EXPORT_SYMBOL(neigh_table_init_no_netlink);
L
Linus Torvalds 已提交
2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778
EXPORT_SYMBOL(neigh_update);
EXPORT_SYMBOL(pneigh_enqueue);
EXPORT_SYMBOL(pneigh_lookup);

#ifdef CONFIG_ARPD
EXPORT_SYMBOL(neigh_app_ns);
#endif
#ifdef CONFIG_SYSCTL
EXPORT_SYMBOL(neigh_sysctl_register);
EXPORT_SYMBOL(neigh_sysctl_unregister);
#endif